CN108334085A - Smart collaboration method, apparatus, system, intelligent terminal and storage medium - Google Patents

Abstract

The embodiment of the present disclosure discloses smart collaboration method, apparatus, system, intelligent terminal and computer readable storage medium.The method operates on the first intelligent terminal, including：When the confidence level of the handling result to the first data is less than the first predetermined threshold value, cooperation request is sent to one or more second intelligent terminals；Receive feedback information of one or more of second intelligent terminals for the cooperation request；The first data described at least one second intelligent terminal collaborative process are selected according to the feedback information.By embodiment of the present disclosure, any one intelligent terminal can share the intelligent capability of neighbouring intelligent terminal so that the ability of single intelligent terminal greatly enhances, and greatly improves user experience.

Description

Intelligent collaboration method, device, system, intelligent terminal and storage medium

technical field

The present disclosure relates to the technical field of intelligent identification, and in particular to an intelligent collaboration method, device, system, intelligent terminal, and computer-readable storage medium.

Background technique

With the development of smart terminal technology and network technology, it has been applied to more complex usage environments, such as robots, self-driving cars, drones, smart homes and other fields. With the complexity of the environment, the ability to perceive and judge the environment is also constantly improving. Therefore, artificial intelligence algorithms are also constantly developing, and the computing power requirements for smart terminals are also higher. Moreover, due to the inconsistency of application scenarios and learning and training processes of artificial intelligence algorithms, there will be differences in their capabilities, resulting in the emergence of a single smart terminal. Computation will be limited by its own hardware performance and intelligence capabilities, and there is a problem that calculations cannot be completed.

Contents of the invention

Embodiments of the present disclosure provide an intelligent collaboration method, device, electronic equipment, and computer-readable storage medium.

In the first aspect, an embodiment of the present disclosure provides an intelligent collaboration method, the method runs on the first intelligent terminal, including:

When the confidence level of the processing result of the first data is lower than a first preset threshold, sending a cooperation request to one or more second smart terminals;

receiving feedback information from the one or more second smart terminals on the cooperation request;

Selecting at least one second smart terminal to cooperatively process the first data according to the feedback information.

Wherein, the collaboration request includes the first data.

Wherein, the first data includes at least one of image, sound, key and radar data.

Wherein, the feedback information includes: the intelligence capability index of the second smart terminal and/or the identity information of the second smart terminal.

Wherein, the intelligence ability index includes at least one of the following:

The intelligence capability index is an intelligence capability index for the first data;

The intelligent capability index is determined in advance according to the performance of the second intelligent terminal;

The smart capability index is a capability index determined in advance according to the processing capability of the second smart terminal for the first data.

Wherein, the feedback information includes a processing result of the first data.

Wherein, selecting at least one second smart terminal to cooperatively process the first data according to the feedback information includes:

determining the processing capability of the second smart terminal for the first data according to the feedback information;

When the processing capability is greater than a second preset threshold, the at least one second smart terminal is selected to cooperatively process the first data.

Wherein, determining the processing capability of the second smart terminal for the first data according to the feedback information includes:

Determine the processing capability according to the intelligence capability index of the second smart terminal in the feedback information, and/or,

The processing capability is determined according to a processing result of the first data by the second smart terminal in the feedback information.

Wherein, when receiving feedback information from multiple second smart terminals with the same processing capability, selecting at least one second smart terminal to cooperatively process the first data according to the feedback information includes:

Selecting the second smart terminal with the shortest feedback time.

Wherein, when receiving feedback information from a plurality of second smart terminals with the same processing capability, selecting at least one second smart terminal to cooperatively process the first data according to the feedback information, further comprising:

When the feedback time of the plurality of second smart terminals with the same processing capability is also the same, acquire processing results of the first data by the plurality of second smart terminals with the same processing capability;

When the processing results are different, sending second data to the plurality of second smart terminals with the same processing capability; the second data is different from the first data.

Wherein, selecting at least one second smart terminal to cooperatively process the first data according to the feedback information further includes:

Selecting at least one second smart terminal from the plurality of second smart terminals with the same processing capability to cooperatively process the first data according to the processing results of the second data by the plurality of second smart terminals with the same processing capability .

Wherein, when receiving feedback information from multiple second smart terminals with the same processing capability, selecting at least one second smart terminal to cooperatively process the first data according to the feedback information includes:

Acquiring multiple processing results of the first data by the multiple second smart terminals with the same processing capability;

clustering the multiple processing results when the multiple processing results are different;

The processing result with the largest number is selected according to the clustering result as the cooperative processing result of the first data.

In the second aspect, an embodiment of the present disclosure provides an intelligent collaboration device, the device runs on a first intelligent terminal, including:

A sending module configured to send a cooperation request to one or more second smart terminals when the confidence level of the processing result of the first data is lower than a first preset threshold;

A receiving module configured to receive feedback information from the one or more second smart terminals on the cooperation request;

A selection module configured to select at least one second smart terminal to cooperatively process the first data according to the feedback information.

Wherein, the collaboration request includes the first data.

Wherein, the first data includes at least one of image, sound, key and radar data.

Wherein, the feedback information includes: the intelligence capability index of the second smart terminal and/or the identity information of the second smart terminal.

Wherein, the intelligence ability index includes at least one of the following:

The intelligence capability index is an intelligence capability index for the first data;

The intelligent capability index is determined in advance according to the performance of the second intelligent terminal;

The smart capability index is a capability index determined in advance according to the processing capability of the second smart terminal for the first data.

Wherein, the feedback information includes a processing result of the first data.

Wherein, the selected modules include:

The first determining submodule is configured to determine the processing capability of the second smart terminal for the first data according to the feedback information;

The first selection submodule is configured to select the at least one second smart terminal to cooperatively process the first data when the processing capability is greater than a second preset threshold.

Wherein, the first determining submodule includes:

The second determining submodule is configured to determine the processing capability according to the intelligent capability index of the second smart terminal in the feedback information, and/or,

The third determining submodule is configured to determine the processing capability according to a processing result of the first data by the second smart terminal in the feedback information.

Wherein, when receiving feedback information from multiple second smart terminals with the same processing capability, the selected module includes:

The second selection submodule is configured to select the second smart terminal with the shortest feedback time.

Wherein, when receiving feedback information from a plurality of second intelligent terminals with the same processing capability, the selection module further includes:

The first acquisition submodule is configured to obtain the processing of the first data by the plurality of second smart terminals with the same processing capacity when the feedback time of the plurality of second smart terminals with the same processing capacity is also the same result;

The sending submodule is configured to send second data to the plurality of second smart terminals having the same processing capability when the processing results are different; the second data is different from the first data.

Wherein, the selected modules also include:

The third selection sub-module is configured to select at least one second intelligent terminal from the plurality of second intelligent terminals with the same processing capability according to the processing results of the second data by the plurality of second intelligent terminals with the same processing capability The two smart terminals cooperate to process the first data.

Wherein, when receiving feedback information from multiple second smart terminals with the same processing capability, the selected module includes:

The second acquiring submodule is configured to acquire multiple processing results of the first data by the multiple second smart terminals with the same processing capability;

The clustering submodule is configured to cluster the multiple processing results when the multiple processing results are different;

The fourth determination submodule is configured to select the processing result with the largest number as the collaborative processing result of the first data according to the clustering result.

The functions described above may be implemented by hardware, or may be implemented by executing corresponding software on the hardware. The hardware or software includes one or more modules corresponding to the above functions.

In a possible design, the structure of the intelligent cooperation device includes a memory and a processor, the memory is used to store one or more computer instructions that support the intelligent cooperation device to execute the intelligent cooperation method in the first aspect above, and the processor configured to execute computer instructions stored in said memory. The intelligent cooperation device may also include a communication interface, which is used for the intelligent cooperation device to communicate with other devices or a communication network.

In a third aspect, an embodiment of the present disclosure provides an intelligent collaboration system, including:

The first smart terminal includes the smart collaboration device as described in the second aspect;

At least one second intelligent terminal.

In a fourth aspect, an embodiment of the present disclosure provides a first smart terminal, including a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are stored by the The processor executes to implement the method steps described in the first aspect.

In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer instructions used by an intelligent collaboration device, including computer instructions for executing the intelligent collaboration method in the first aspect above.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

The embodiments of the present disclosure are mainly applied to smart terminals. When a smart terminal is processing certain or certain data, if it has insufficient ability to process the data or the result of processing the data is unsatisfactory, it can request cooperation from other smart terminals around. Processing, after receiving feedback information from other smart terminals, select one or more other smart terminals to cooperatively process the data according to the feedback information. Through the embodiments of the present disclosure, any smart terminal can share the smart capabilities of adjacent smart terminals, so that the capabilities of a single smart terminal are greatly enhanced, and user experience is greatly improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

Other features, objects and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the attached picture:

FIG. 1 shows a flowchart of an intelligent collaboration method according to an embodiment of the present disclosure;

Fig. 2 shows a schematic diagram of a smart car collaboration scenario according to an embodiment of the present disclosure;

FIG. 3 shows a flow chart of step S103 according to the embodiment shown in FIG. 1;

FIG. 4 shows another flowchart of step S103 according to the embodiment shown in FIG. 1;

FIG. 5 shows another flowchart of step S103 according to the embodiment shown in FIG. 1;

Fig. 6 shows a structural block diagram of an intelligent collaboration device according to an embodiment of the present disclosure;

Fig. 7 is a schematic structural diagram of an electronic device suitable for implementing a smart collaboration method according to an embodiment of the present disclosure.

Detailed ways

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for clarity, parts not related to describing the exemplary embodiments are omitted in the drawings.

In the present disclosure, it should be understood that terms such as "comprising" or "having" are intended to indicate the presence of features, numbers, steps, acts, components, parts or combinations thereof disclosed in the specification, and are not intended to exclude one or a plurality of other features, numbers, steps, acts, parts, parts or combinations thereof exist or are added.

In addition, it should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

At present, cloud computing is mainly used to make up for the lack of computing power of a single intelligent terminal. This technical solution requires network support. Due to reasons such as transmission distance and network composition, it may cause network delays, and there are insufficient intelligent capabilities in emergency situations. The problem. Therefore, a collaborative computing method based on a local ad hoc network has emerged. In the collaborative computing process, it is necessary to find one or more appropriate smart terminals for collaborative computing, or to evaluate the computing results of each smart terminal to determine the cooperative computing method. The algorithm is the main problem at present.

Fig. 1 shows a flowchart of an intelligent collaboration method according to an embodiment of the present disclosure. As shown in Figure 1, the intelligent collaboration method runs on the first intelligent terminal, including the following steps S101-S103:

In step S101, when the confidence level of the processing result of the first data is lower than a first preset threshold, a cooperation request is sent to one or more second smart terminals;

In step S102, receiving feedback information of the cooperation request from the second smart terminal;

In step S103, at least one second smart terminal is selected according to the feedback information to cooperatively process the first data.

In this embodiment, the first smart terminal and the second smart terminal may be smart terminals with smart capabilities such as smart cars, smart industrial robots, smart phones, and smart homes. Smart terminals may have different smart capabilities due to their different application directions. The intelligence capability represents the data processing level of the smart terminal in a certain aspect. This level will vary due to the hardware performance of the smart terminal and/or the smart algorithm loaded by the manufacturer to the smart terminal when it leaves the factory, and also due to the Differences due to evolutionary learning. For example, take smart car obstacle avoidance as an example. Obstacle avoidance is a basic function that a smart car needs to have, and the identification of obstacles is the first step to complete obstacle avoidance. Different manufacturers of smart cars have different intelligent algorithms loaded in the on-board smart system at the factory. Even if the same manufacturer , after learning and training in the actual road driving process, there will be differences in the intelligent system of the vehicle, so there are also differences in the ability to identify obstacles. The intelligent ability of intelligent vehicles to identify obstacles is calibrated through the intelligent ability test, which is used to represent intelligent vehicles. obstacle recognition ability.

Therefore, due to the limitation of the intelligent ability of the first intelligent terminal, when processing the first data, when the data cannot be processed or the processing result is unsatisfactory, that is, the confidence level is lower than the first preset threshold, it can send a cooperation request to seek help from other The smart terminal cooperates to process the first data. The confidence degree of the first smart terminal for the processing result of the first data may set different measurement standards according to the attributes, processing methods and processing results of the first data. For example, when the first intelligent terminal uses the trained artificial intelligence model to process the first data, the output result is presented as the probability value of each output of the artificial intelligence model. For example, the artificial intelligence model has three outputs, which are A, B, and C respectively. The result obtained after inputting a piece of data into the artificial intelligence model is {A: 90%, B: 10, C: 5%}. At this time, it can be considered that the processing result of the first data is A. However, if the probability values of any two of the three outputs are very similar, such as 90% for A and 85% for B, then it is impossible to determine whether the processing result of the first data is A or B. If the similarity between the two outputs of the artificial intelligence model with a probability value higher than 50% is within a predetermined range, it is considered that the confidence of the processing result is lower than the first preset threshold. Of course, it is understandable that there may be other ways to measure the confidence, for example, all the output probability values of the artificial intelligence model are lower than 50%, etc., which are set according to the actual situation and are not limited here.

In an embodiment, the second smart terminal may be the same type of smart terminal as the first smart terminal, or may be a different type of smart terminal. For example, the first smart terminal is a smart car, and the second smart terminal is also a smart car; the first smart terminal is a smart speaker, and the second smart terminal is a smart TV. The first smart terminal may send a cooperation request to the second smart terminal through a wireless communication network, such as wifi, NFC approach communication, Bluetooth, Zigbee and other wireless communication networks.

In an embodiment, the cooperation request may be a request containing a certain standardized intelligent capability, the second intelligent terminal may be preset to be able to identify the cooperation request, and the intelligent capability of the second intelligent terminal may be evaluated in advance through an evaluation method . The feedback information of the second smart terminal may include the smart capability index of the second smart terminal.

Optionally, the intelligence capability index includes at least one of the following:

The intelligence capability index is an intelligence capability index for the first data;

The intelligent capability index is determined in advance according to the performance of the second intelligent terminal;

The smart capability index is a capability index determined in advance according to the processing capability of the second smart terminal for the first data.

For example, under a specific intelligent task, an accuracy index is set, and after the second intelligent terminal can exceed the accuracy index, it is considered that the intelligent terminal has the intelligent capability. For example, the intelligence capability can be distinguished according to the ability of the second intelligent terminal to accurately classify a certain type of data, or it can be divided into different levels according to the accuracy of the result of executing a certain task. An example of an existing intelligence capability index can be obtained from the current definition of unmanned vehicles. Levels L1-L5 of unmanned vehicles correspond to the level of autonomous driving capabilities of the unmanned vehicles, so this level can also be considered as An index of intellectual capability. For another example, natural speech recognition can be used as an intelligence index through its applicable language types. The intelligence ability can be fixed for a certain period of time, or it can be gradually improved with the improvement of methods or data. In addition, intelligence capabilities also include the level of data processing capabilities, such as the time or energy consumed to process the same task can also be used as an evaluation standard for intelligence capabilities. Therefore, the same standard can be used in different smart terminals to define a series of smart capabilities.

In an embodiment, the feedback information may also include identity information of the second smart terminal. Optionally, the identity information of the second smart terminal may be the holder information of the second smart terminal. In other embodiments, the identity information of the second smart terminal may also include attribute information such as brand, signal, and device type of the second smart terminal.

In an embodiment, the collaboration request may further include first data. The first data includes at least one of image, sound, key and radar data. The first smart terminal processes the first data to identify relevant information in the first data, or classifies the first data, so as to realize the next step of intelligent processing. For example, in the process of automatic driving, a smart car can recognize roadblocks based on the acquired images, and then select the next driving direction. The second smart terminal may also perform corresponding processing on the first data in the cooperation request after receiving the cooperation request, such as identifying obstacles in the image data according to the cooperation request when the first data is image data.

In an embodiment, the feedback information of the second smart terminal for the cooperation request may further include a processing result for the first data in the cooperation request. For example, the first data included in the cooperation request is the image data captured by the first smart terminal such as a smart car during automatic driving. After receiving the image data, the second smart terminal recognizes obstacles on the image data and The object recognition result is fed back to the first smart terminal.

After receiving the feedback information from the second smart terminal, the first smart terminal may determine whether to select the second smart terminal as the cooperative processing terminal based on the smart capability fed back by the second smart terminal and/or the processing result of the first data. In the case where the second smart terminal only feeds back its smart capabilities, the first smart terminal determines whether the second smart terminal meets the needs of this cooperative processing through the analysis of the smart capabilities of the second smart terminal, that is, whether it can process the first data, and Based on the analysis results, it is determined whether to select the second smart terminal as the cooperative processing terminal; when the second smart terminal feeds back the intelligent capability or when the processing result of the first data is fed back separately, the first smart terminal can also be based on the second smart terminal's The processing result of the first data determines whether the processing result of the first data by the second smart terminal meets the requirements. For example, whether the second smart terminal recognizes the obstacle in the first data or not. After the first smart terminal receives feedback information from multiple second smart terminals, the second smart terminal that is the best or most suitable for processing the first data may be selected as the cooperative processing terminal based on the feedback information.

The above-mentioned intelligent collaboration method will be further described below through usage scenarios of the above-mentioned embodiments of the present disclosure.

Application Scenario 1: This embodiment takes smart car obstacle avoidance as an example. As shown in FIG. Obstacle training, so the first smart car 201 cannot recognize the obstacle, but it can determine that the object is an obstacle 204, and through the trained obstacle recognition algorithm, the confidence of the recognition result is lower than a predetermined threshold, indicating that it cannot recognize The obstacle 204 . At this time, the first smart car 201 sends a cooperation request message 2012 to other nearby smart cars through short-distance wireless data transmission. The cooperation request message 2012 may include a standardized smart capability request, such as asking the other party's level of automatic driving, traffic lights, etc. recognition ability, etc. The cooperation request information may also include obstacle image data, and the smart car receiving the cooperation request is, in this embodiment, there are two smart cars near the first smart car 201, the first cooperative smart car 202 and the second cooperative smart car 203; After the first cooperative smart car 202 and the second cooperative smart car 203 receive the cooperation request information, the first cooperative smart car 202 feeds back a piece of information 2021, and the feedback information 2021 may include the intelligent capabilities corresponding to the identity information and the cooperation demand information. After a smart car 201 receives the feedback information 2021, if the smart capability of the first cooperative smart car 202 is higher than that of the second cooperative smart car 203, the processing result of the first cooperative smart car is selected. Among them, the intelligent capability of the feedback can be obtained according to the directional query of the collaboration information. For example, the collaboration information includes inquiry information asking whether a certain intelligent capability is included, and the feedback information can include a list of capabilities or an answer of whether or not. The intelligent capability of the feedback can also be judged according to the sent task, for example, the corresponding intelligent capability obtained after processing the collaboration request data. For example, the request information contains image information of unrecognizable obstacle recognition, and the collaborative smart car finds the corresponding intelligent ability of the model through the recognition model used in the process of recognizing the image, and includes this ability in the feedback information.

Application Scenario 2, this embodiment takes smart home voice control as an example. Voice control is an important control method of smart home. The recognition of voice commands is the premise of realizing voice control. When the smart home products of different smart home manufacturers leave the factory, they will be loaded with voice command recognition algorithms, and some manufacturers will even load them. Dialect recognition algorithm, but the differences in the pronunciation of languages around the world and the differences in local dialects lead to the problem that a new smart home product cannot recognize voice commands when it first provides services to customers, and smart home products that have been used for a period of time have already The user's dialect is applied, and the user's voice commands can be correctly recognized. Therefore, when a newly purchased smart home product cannot recognize voice control commands, it needs to request other smart home products to cooperate in recognition. For example, a smart TV is a newly purchased smart home product. When the user sends out the command "Turn on the TV" in a dialect, the voice input sensor of the smart TV acquires the user's voice command. Because it has not been trained in the user's dialect, the smart TV built-in The voice recognition algorithm cannot recognize the command or the confidence level of the recognition is lower than the threshold, indicating that it cannot recognize the voice command; the smart TV sends a collaboration request message to other nearby smart home products through wireless communication transmission, and the collaboration request message includes the acquired voice data, Other smart home products that receive the collaboration request. In this embodiment, other smart home products include smart lights, smart thermometers, smart kettles, smart speakers, and tablet computers; The data is processed, and feedback information is obtained according to the processing results. For example, if the segment of speech can be recognized correctly, it means that a corresponding intelligent ability has been discovered, and through the recognition of the segment of speech data, the corresponding dialect information can be identified, so it is found that it corresponds to a more specific classification of intelligent ability, for example {Intelligence ability: x dialect recognition ability}. Afterwards, an information containing these contents is fed back, and the feedback information includes the identity information and the intelligence capability information corresponding to the cooperation requirement information. After receiving the feedback information, the smart TV can select a cooperation object according to the feedback information.

In an optional implementation of this embodiment, as shown in FIG. 3, the step S103, that is, the step of selecting at least one second smart terminal to cooperatively process the first data according to the feedback information, further includes the following Steps S301-S302:

In step S301, determine the processing capability of the second smart terminal for the first data according to the feedback information;

In step S302, when the processing capability is greater than a second preset threshold, the at least one second smart terminal is selected to cooperatively process the first data.

In this optional implementation manner, the feedback information may include an intelligence capability index of the second smart terminal and/or a processing result of the first data.

In an embodiment, the processing capability is determined according to the intelligence capability index of the second smart terminal in the feedback information. The smart terminal can include a variety of different smart capability indexes for different data, for example, the smart capability index of the same smart terminal for image recognition is higher than 90%, while the smart capability index for speech recognition is lower than 50%, the second smart terminal The corresponding intelligence capability index can be fed back based on the specific requirements in the collaboration request, or all existing intelligence capability indexes can be fed back. The first smart terminal determines the capability of the second smart terminal to process the first data based on the smart capability index in the feedback information. For example, when the first data is image data, the processing capability of the second smart terminal is higher than 90%. The processing capability of the second smart terminal is greater than the second preset threshold, and when the first data is voice data, the processing capability of the second smart terminal is lower than 50%, and it can be considered that the processing capability of the second smart terminal is smaller than the second preset threshold. The second preset threshold can be preset based on experience and actual conditions.

In another embodiment, the processing capability is determined according to a processing result of the first data by the second smart terminal in the feedback information. When the cooperation request includes the first data, the second smart terminal can also directly feed back the processing result of the first data to the first smart terminal if it can process the first data, and the first smart terminal can The processing result determines the processing capability of the second smart terminal. For example, if the first data is image data, and the first smart terminal cannot identify the type of obstacle in the image, but the type of obstacle is identified in the feedback information of the second smart terminal, the processing capability of the second smart terminal is greater than that of the first smart terminal. The threshold is preset, and the second smart terminal can be selected as the collaborative processing terminal.

Of course, it can be understood that when the feedback information includes both the intelligence capability index and the processing result of the first data, the first smart terminal can also comprehensively consider the intelligence capability index and the processing result of the second data to select the optimal The second smart terminal is used as a collaborative processing terminal.

In an optional implementation of this embodiment, when receiving feedback information from multiple second smart terminals with the same processing capability, the step S301 is to select at least one second smart terminal to cooperate with The step of processing the first data further includes the following steps:

Selecting the second smart terminal with the shortest feedback time.

In this optional implementation, when feedback information from multiple second smart terminals is received and multiple second smart terminals have the same processing capability for the first data, the second smart terminal with the shortest feedback time can be selected as the cooperative processing terminal. By analyzing the intelligence capability index or the processing result of the first data, when it is determined that multiple second intelligent terminals have the same intelligence capability, select the second intelligent terminal that receives the feedback information first as the cooperative processing terminal. In this way, in the case of the same capability, selecting the second intelligent terminal with the best real-time performance can save time and cost and improve real-time performance.

In an optional implementation of this embodiment, as shown in FIG. 4 , when receiving feedback information from multiple second smart terminals with the same processing capability, the step S103 is to select at least The step of cooperatively processing the first data by a second smart terminal further includes the following steps S401-S402:

In step S401, when the feedback time of the plurality of second smart terminals with the same processing capability is also the same, obtain the processing results of the first data by the plurality of second smart terminals with the same processing capability;

In step S402, when the processing results are different, send second data to the plurality of second smart terminals with the same processing capability; the second data is different from the first data.

In this optional implementation, when there are multiple second intelligent terminals with the same intelligence capabilities and the same feedback time, it is relatively simple to randomly select one of them as a cooperative processing terminal; but in order to obtain the most In order to obtain the best effect, it is also possible to choose to determine the cooperative terminal by analyzing the processing results of the first data by multiple second smart terminals. If the feedback information does not include the processing results of the first data, the first data may be sent to the second smart terminal. When the processing results of the first data by multiple second terminals are obtained, if the multiple second terminals If the processing result of the first data is different, the second data may be sent to the second smart terminal, and the second data and the first data may be different data for the same object. For example, the first data is a photo of an obstacle taken by the smart car from a first angle, and the second data is another photo of the same obstacle taken by the smart car from a second angle. Even if the intelligence capabilities are the same, the recognition results for the same data are different due to the differences in their training algorithms and training samples. Therefore, by sending the second data, the recognition capability of multiple second smart terminals for the same object is further verified.

In an optional implementation of this embodiment, when receiving feedback information from multiple second smart terminals with the same processing capability, the step S103 is to select at least one second smart terminal to cooperate The step of processing the first data also includes the following steps:

Selecting at least one second smart terminal from the plurality of second smart terminals with the same processing capability to cooperatively process the first data according to the processing results of the second data by the plurality of second smart terminals with the same processing capability .

In this optional implementation, after the processing result of the second data is obtained, a second smart terminal is determined as a cooperative processing terminal according to the processing result of the second data, and its processing result for the first data is selected.

In an optional implementation of this embodiment, as shown in FIG. 5 , when receiving feedback information from multiple second smart terminals with the same processing capability, the step S301 is to select at least A second smart terminal cooperatively processing the first data step further includes the following steps:

In step S501, multiple processing results of the first data by the multiple second smart terminals with the same processing capability are obtained;

In step S502, clustering the multiple processing results when the multiple processing results are different;

In step S503, the processing result with the largest number is selected as the collaborative processing result of the first data according to the clustering result.

In this optional implementation, when there are multiple second smart terminals with the same intelligent capability and the same feedback time, the first data can be sent to the second smart terminal at the same time, so as to obtain the second smart terminal's A plurality of processing results of the first data. If the multiple second smart terminals have different processing results for the first data, clustering the multiple processing results may also select a type of processing results with a larger number as the final processing results of the first data. In this way, the processing results of multiple second smart terminals for the first data can be comprehensively considered, and according to the principle that the majority obeys the minority, the second smart terminal that gives the largest number of the same processing results can be selected as the cooperative processing terminal, and the processing results As the final processing result of the first data. In this way, the processing results of multiple second intelligent terminals are integrated, which overcomes the one-sidedness, and because there is no need to send the second data for processing, the processing time is shortened and the real-time performance is improved.

The following are device embodiments of the present disclosure, which can be used to implement the method embodiments of the present disclosure.

Fig. 6 shows a structural block diagram of an intelligent cooperation device according to an embodiment of the present disclosure, and the device may be implemented as part or all of an electronic device through software, hardware or a combination of the two. As shown in Figure 6, the intelligent collaboration device includes a sending module 601, a receiving module 602 and a selection module 603:

The sending module 601 is configured to send a cooperation request to one or more second smart terminals when the confidence level of the processing result of the first data is lower than a first preset threshold;

A receiving module 602 configured to receive feedback information from the one or more second smart terminals on the cooperation request;

The selecting module 603 is configured to select at least one second smart terminal to cooperatively process the first data according to the feedback information.

The collaboration request includes the first data.

In an optional implementation manner of this embodiment, the first data includes at least one of image, sound, key and radar data.

In an optional implementation manner of this embodiment, the feedback information includes: an intelligence capability index of the second smart terminal and/or identity information of the second smart terminal.

In an optional implementation of this embodiment, the intelligence capability index includes at least one of the following:

The intelligence capability index is an intelligence capability index for the first data;

The intelligent capability index is determined in advance according to the performance of the second intelligent terminal;

The smart capability index is a capability index determined in advance according to the processing capability of the second smart terminal for the first data.

In an optional implementation manner of this embodiment, the feedback information includes a processing result of the first data.

In an optional implementation of this embodiment, the selected module includes:

The first determining submodule is configured to determine the processing capability of the second smart terminal for the first data according to the feedback information;

The first selection submodule is configured to select the at least one second smart terminal to cooperatively process the first data when the processing capability is greater than a second preset threshold.

In an optional implementation manner of this embodiment, the first determining submodule includes:

The second determining submodule is configured to determine the processing capability according to the intelligent capability index of the second smart terminal in the feedback information, and/or,

The third determining submodule is configured to determine the processing capability according to a processing result of the first data by the second smart terminal in the feedback information.

In an optional implementation of this embodiment, when receiving feedback information from multiple second smart terminals with the same processing capability, the selection module includes:

The second selection submodule is configured to select the second smart terminal with the shortest feedback time.

In an optional implementation of this embodiment, when receiving feedback information from multiple second smart terminals with the same processing capability, the selecting module further includes:

The first acquisition submodule is configured to obtain the processing of the first data by the plurality of second smart terminals with the same processing capacity when the feedback time of the plurality of second smart terminals with the same processing capacity is also the same result;

The sending submodule is configured to send second data to the plurality of second smart terminals having the same processing capability when the processing results are different; the second data is different from the first data.

In an optional implementation of this embodiment, the selected module further includes:

The third selection sub-module is configured to select at least one second intelligent terminal from the plurality of second intelligent terminals with the same processing capability according to the processing results of the second data by the plurality of second intelligent terminals with the same processing capability The two smart terminals cooperate to process the first data.

In an optional implementation of this embodiment, when receiving feedback information from multiple second smart terminals with the same processing capability, the selection module includes:

The second acquiring submodule is configured to acquire multiple processing results of the first data by the multiple second smart terminals with the same processing capability;

The clustering submodule is configured to cluster the multiple processing results when the multiple processing results are different;

The fourth determination submodule is configured to select the processing result with the largest number as the collaborative processing result of the first data according to the clustering result.

The present disclosure also provides an intelligent collaboration system, including:

The first intelligent terminal includes the intelligent collaboration device as described in FIG. 6 and related embodiments;

At least one second intelligent terminal.

Fig. 7 is a schematic structural diagram of a first smart terminal adapted to implement a smart collaboration method according to an embodiment of the present disclosure.

As shown in FIG. 7, the first intelligent terminal 700 includes a central processing unit (CPU) 701, which can be loaded into a random access memory (RAM) 703 according to a program stored in a read-only memory (ROM) 702 or from a storage part 708. various processes in the embodiment shown in FIG. 1 described above. Various programs and first data required for the operation of the first smart terminal 700 are also stored in the RAM 703 . The CPU 701 , ROM 702 , and RAM 703 are connected to each other via a bus 704 . An input/output (I/O) interface 705 is also connected to the bus 704 .

The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 708 including a hard disk, etc. and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 710 as necessary so that a computer program read therefrom is installed into the storage section 708 as necessary.

In particular, according to an embodiment of the present disclosure, the method described above with reference to FIG. 1 may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable therefrom, the computer program comprising program code for performing the method of FIG. 1 . In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709 and/or installed from a removable medium 711 .

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a roadmap or block diagram may represent a module, program segment, or part of code that contains one or more Executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units or modules involved in the embodiments described in the present disclosure may be implemented by means of software or hardware. The described units or modules may also be set in the processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.

As another aspect, the present disclosure also provides a computer-readable storage medium. The computer-readable storage medium may be the computer-readable storage medium included in the device described in the above-mentioned embodiments; A computer-readable storage medium assembled in a device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the methods described in the present disclosure.

The above description is only a preferred embodiment of the present disclosure and an illustration of the applied technical principle. It should be understood by those skilled in the art that the scope of the invention involved in this disclosure is not limited to the technical solution formed by the specific combination of the above technical features, but also covers the technical solutions made by the above technical features without departing from the inventive concept. Other technical solutions formed by any combination of or equivalent features thereof. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims (10)

1. An intelligent cooperation method, which is operated on a first intelligent terminal, comprises the following steps:

when the confidence coefficient of the processing result of the first data is lower than a first preset threshold value, sending a cooperation request to one or more second intelligent terminals;

receiving feedback information of the one or more second intelligent terminals for the cooperation request;

and selecting at least one second intelligent terminal to cooperatively process the first data according to the feedback information.

2. The intelligent collaboration method of claim 1, wherein the collaboration request includes the first data.

3. The intelligent collaboration method of claim 1, wherein the first data comprises at least one of image, sound, key, and radar data.

4. The intelligent collaboration method of claim 1, wherein the feedback information comprises: the intelligent capability index of the second intelligent terminal and/or the identity information of the second intelligent terminal.

5. The intelligent collaboration method of claim 4, wherein the intelligent capability index comprises at least one of:

the intelligent capability index is an intelligent capability index for the first data;

the intelligent capability index is determined in advance according to the performance of the second intelligent terminal;

the intelligent capability index is a capability index determined in advance according to the processing capability of the second intelligent terminal on the first data.

6. The intelligent collaboration method of claim 1, wherein the feedback information comprises a result of processing the first data.

7. An intelligent cooperation apparatus, wherein the apparatus runs on a first intelligent terminal, comprising:

the sending module is configured to send a cooperation request to one or more second intelligent terminals when the confidence of the processing result of the first data is lower than a first preset threshold;

a receiving module configured to receive feedback information of the one or more second intelligent terminals on the cooperation request;

and the selecting module is configured to select at least one second intelligent terminal to cooperatively process the first data according to the feedback information.

8. An intelligent collaboration system, comprising:

a first intelligent terminal comprising the intelligent collaboration apparatus of claim 7;

and at least one second intelligent terminal.

9. A first intelligent terminal, comprising a memory and a processor; wherein,

the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any of claims 1-6.

10. A computer-readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, carry out the method steps of any of claims 1-6.